import datetime
import glob
from IPython.display import HTML
import numpy as np
import numpy_financial as npf
import os
import pandas as pd
import plotly.express as px
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import sys

module_path = os.path.abspath(os.path.join('..'))
if module_path not in sys.path:
    sys.path.append(module_path)

import data_analysis as data_analysis
import data_visualization as data_vis

import plotly.io as pio
pio.templates.default = 'plotly_white'
pio.renderers.default = 'notebook'

# Set paths to where data is stored
data_dir = '/Users/jenny.folkesson/Data/solar/'
dgstats_dir = os.path.join(data_dir, 'applications_20251231/')
archive_dir = os.path.join(data_dir, 'Interconnection_Applications_Dataset_2024-12-31/')
logo_path = "https://solarwaveaction.org/assets/images/SolarWAVEActionLogoTransparent.png"

df_total = data_analysis.read_stored_data(dgstats_dir, "dgstats_preprocessed_data.csv", archive_dir)

Reading existing file:  /Users/jenny.folkesson/Data/solar/applications_20251231/dgstats_preprocessed_data.csv

df_scci = df_total.copy()
df_scci = df_scci[df_scci['Service County'].str.lower() == 'santa cruz']
df_scci = df_scci[(df_scci['Customer Sector'] == 'Commercial') | (df_scci['Customer Sector'] == 'Industrial')]

# Inspect data
df_scci

fig = data_vis.dgstats_vs_pge_bargraph(df_total)

# Write figure
fig.write_image(os.path.join(data_dir, "DGStats_vs_PGE.png"), scale=5)
fig.write_html(os.path.join(data_dir, "DGStats_vs_PGE.html"),
               include_plotlyjs='cdn',
               full_html=False,
               config={"responsive": True}
)
# Display figure
html_str = fig.to_html(include_plotlyjs='cdn', full_html=False)
HTML(html_str)

# PGE application decrease after 2022
app_change = (438 - 3100) / 3100 * 100
print("Application volume change: {:.1f}%".format(app_change))

Application volume change: -85.9%

df = df_scci.copy()
df['Year'] = df['App Approved Date'].dt.year
df = df[df['Year'] >= 2021]
fig = px.histogram(df, x='System Size DC', color='Customer Sector')

fig.update_layout(
    autosize=False,
    width=800,
    height=400,
    font=dict(size=12),
    xaxis_title='System Size DC (kW)',
    yaxis_title='Nbr of Applications',
)
fig.update_yaxes(
    range=[0, 100],
)
# Write figure
fig.write_image(os.path.join(data_dir, "SC_system_histogram.png"), scale=5)
fig.write_html(os.path.join(data_dir, "SC_system_histogram.html"),
               include_plotlyjs='cdn',
               full_html=False,
               config={"responsive": True}
)
# Display figure
html_str = fig.to_html(include_plotlyjs='cdn', full_html=False)
HTML(html_str)

# Application sizes
nbr_app = df.shape[0]
print("Percentage of projects < 50 kW: {:.1f}%".format(93 / nbr_app * 100))
print("Percentage of projects < 100 kW: {:.1f}%".format( (93 + 21) / nbr_app * 100))

Percentage of projects < 50 kW: 69.4%
Percentage of projects < 100 kW: 85.1%

# Median application data
df = df_scci.copy()
df = df[df['App Approved Date'].dt.year >= 2021]
# Median capacity
print("Median capacity DC: {} kW".format(df['System Size DC'].median()))

# Median tilt
df['Tilt'] = pd.to_numeric(df['Tilt'], errors='coerce')
print("Median tilt: {} degrees".format(df['Tilt'].median()))

# Median azimuth
df['Azimuth'] = pd.to_numeric(df['Azimuth'], errors='coerce')
print("Median azimuth: {} degrees".format(df['Azimuth'].median()))

Median capacity DC: 0.029908499999999998 kW
Median tilt: 18.0 degrees
Median azimuth: 180.0 degrees

fig = data_vis.application_time_bargraph(df_scci)

# Write figure
fig.write_image(os.path.join(data_dir, "SC_application_time.png"), scale=5)
fig.write_html(os.path.join(data_dir, "SC_application_time.html"),
               include_plotlyjs='cdn',
               full_html=False,
               config={"responsive": True}
)
# Display figure
html_str = fig.to_html(include_plotlyjs='cdn', full_html=False)
HTML(html_str)

import importlib
importlib.reload(data_vis)
fig = data_vis.commercial_capacity_per_year(df_scci)

# Write figure
title_text = "How AB 2143 Derailed Commercial Solar Adoption in Santa Cruz County"
caption_text = "Commercial and industrial system capacity (MW) added quarterly in Santa Cruz County in the years 2021-25.<br>Data Source: California DG Statistics"
data_vis.write_fig(fig, os.path.join(data_dir, "SC_capacity"), title=title_text, caption=caption_text, logo_path=logo_path)
# Display figure
html_str = fig.to_html(include_plotlyjs='cdn', full_html=False)
HTML(html_str)

df = df_scci.copy()
df = df[['App Received Date', 'System Size DC']]
df = df.set_index('App Received Date').rename_axis(None)
df['Nbr Applications'] = 1
df = df.groupby(df.index.year).sum()
df = df[df.index > 2012]
df

# Median and mean application volume in the years 2013-22
df = df[df.index <= 2022]
print("Mean number of applications: ", df['Nbr Applications'].mean())
print("Median number of applications: ", df['Nbr Applications'].median())

Mean number of applications:  22.3
Median number of applications:  23.0

df = data_analysis.compile_electricity_rates(data_dir, nominal_year=2024)
fig = data_vis.electricity_rates_scatter(df, max_year=2024)

# Display figure
html_str = fig.to_html(include_plotlyjs='cdn', full_html=False)
HTML(html_str)

df = data_analysis.compile_electricity_rates(data_dir, nominal_year=2025)
df = df.set_index(df['Year'])

# Values below are real 2025 USD
incr = (df.loc[2025]['US Comm']/df.loc[2020]['US Comm']) ** (1 / 5)
print("US commercial rate increase: {:.2f}%".format((incr - 1) * 100))
incr5 = (df.loc[2025]['US Comm']/df.loc[2020]['US Comm'] - 1) * 100
print("Over 5 years: {:.1f}%".format(incr5))
incr = (df.loc[2025]['CA Comm']/df.loc[2020]['CA Comm']) ** (1 / 5)
print("CA commercial rate increase: {:.2f}%".format((incr - 1) * 100))
incr5 = (df.loc[2025]['CA Comm']/df.loc[2020]['CA Comm'] - 1) * 100
print("Over 5 years: {:.1f}%".format(incr5))
incr5 = (df.loc[2025]['CA Res']/df.loc[2020]['CA Res'] - 1) * 100
print("CA residential rate increase over 5 years: {:.1f}%".format(incr5))

US commercial rate increase: 0.36%
Over 5 years: 1.8%
CA commercial rate increase: 3.87%
Over 5 years: 20.9%
CA residential rate increase over 5 years: 27.9%

df = data_analysis.cost_forecast(nbr_years=25, production=43300, price=0.35, price_increase=2.75, degradation=0.6)
df[['Production (kWh)', 'Cumulative Savings ($)']]

cost = 29.9 * 4000
print("Upfront Cost: ${:.0f}".format(cost))

Upfront Cost: $119600

cumsav = df.iloc[-1]['Cumulative Savings ($)']
cumsav = float(cumsav.replace(",", ""))
print("Cumulative Savings: ${:.0f}".format(cumsav - cost))

Cumulative Savings: $374182

cash_flow = [-cost] + list(df['Annual Savings ($)'])
irr = npf.irr(cash_flow)
print("IRR: {:.1f}%".format(irr*100))

IRR: 14.0%

importlib.reload(data_analysis)
df = data_analysis.cost_forecast(nbr_years=25, production=45000, price=0.39, price_increase=3.5, degradation=0.5)
df[['Production (kWh)', 'Cumulative Savings ($)']]
for row in df.iterrows():
    print(str(str(row[0]) + ' & ' + row[1]['Production (kWh)'] + ' & '  + row[1]['Rate ($/kWh)'] + ' & ' + row[1]['Cumulative Savings ($)']  + ' ' + chr(92) + chr(92)))

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[21], line 1
----> 1 importlib.reload(data_analysis)
      2 df = data_analysis.cost_forecast(nbr_years=25, production=45000, price=0.39, price_increase=3.5, degradation=0.5)
      3 df[['Production (kWh)', 'Cumulative Savings ($)']]

NameError: name 'importlib' is not defined

cost = 29.9 * 3500
print("Upfront Cost: ${:.0f}".format(cost))

cumsav = df.iloc[-1]['Cumulative Savings ($)']
cumsav = float(cumsav.replace(",", ""))
print("Cumulative Savings: ${:.0f}".format(cumsav - cost))

cash_flow = [-cost] + list(df['Annual Savings ($)'])
irr = npf.irr(cash_flow)
print("IRR: {:.1f}%".format(irr*100))

# 1-3 months of first year electicity savings
print("1-3 months savings: ${:.0f} - ${:.0f}".format(17550/12, 17550/12 * 3))

df = data_analysis.cost_forecast(nbr_years=25, production=45800, price=0.43, price_increase=6, degradation=0.4)
df[['Production (kWh)', 'Cumulative Savings ($)']]

cost = 29.9 * 3000
print("Upfront Cost: ${:.0f}".format(cost))

cumsav = df.iloc[-1]['Cumulative Savings ($)']
cumsav = float(cumsav.replace(",", ""))
print("Cumulative Savings: ${:.0f}".format(cumsav - cost))

cash_flow = [-cost] + list(df['Annual Savings ($)'])
irr = npf.irr(cash_flow)
print("IRR: {:.1f}%".format(irr*100))

# Savings for baseline year 1 * [11, 15]
print("Total savings in SC: ${:.0f} - ${:.0f}".format(17550 * 11, 17550 * 15))

# Over 25 years
print("Total savings in SC: ${:.0f} - ${:.0f}".format(17550 * 11 * 25, 17550 * 15 * 25))

# Emission reduction from typical SC solar installation (PG&E)
print("PG&E Emission reduction: {:.1f} kg CO2e/year.".format(16 * 0.45359237 * 45))

print("CA Average Emission reduction: {:.1f} kg CO2e/year.".format(359 * 0.45359237 * 45))

# 11-15 Santa Cruz commercial solar installations
print("PG&E Emission reduction for 11-15 installations: {:.0f}-{:.0f} kg CO2e/year.".format(16 * 0.45359237 * 45 * 11, 16 * 0.45359237 * 45 * 15))

# Data collected from the power contents label data link above for the three main CA IOUs
# PG&E Greenhouse Gas Emissions Intensity (lbs CO2e/MWh)
data = {'Year': [2024, 2023, 2022, 2021, 2020],
        'PGE': [16, 12, 56, 98, 160],
        'SDGE': [663, 537, 508, 504, 636],
        'SCE': [515, 491, 552, 580, 598]}
df_co2 = pd.DataFrame(data)
df_co2

fig = go.Figure()
fig.add_trace(
    go.Scatter(
        x=df_co2['Year'],
        y=df_co2['PGE'],
        name='PGE',
        mode='lines',
    ),
)
fig.add_trace(
    go.Scatter(
        x=df_co2['Year'],
        y=df_co2['SDGE'],
        name='SDGE',
        mode='lines',
    ),
)
fig.add_trace(
    go.Scatter(
        x=df_co2['Year'],
        y=df_co2['SCE'],
        name='SCE',
        mode='lines',
    ),
)
fig.update_layout(
    yaxis_title='Emissions Intensity (lbs CO2e/MWh)',
    xaxis_title='Year',
    width=800,
    height=400,
    font=dict(size=12),
    xaxis=dict(tickvals=df_co2['Year']),
    legend={'title': 'IOU'},
    hovermode="x unified",
)
fig.update_traces(hovertemplate=None)

# Write figure
fig.write_image(os.path.join(data_dir, "emissions_intensity.png"), scale=5)
fig.write_html(os.path.join(data_dir, "emissions_intensity.html"), 
               include_plotlyjs='cdn',
               full_html=False,
               config={"responsive": True}
)
# Display figure
html_str = fig.to_html(include_plotlyjs='cdn', full_html=False)
HTML(html_str)

	IOU	Application Status	Utility	Service City	Service County	Technology Type	System Size DC	System Size AC	Storage Capacity (kWh)	Storage Size (kW AC)	...	Decommissioned Date	Self Installer	Installer Name	Third Party Owned	Third Party Name	Pace Financed	Total System Cost	Cost/Watt	NEM Tariff	Interconnection Program
548276	PGE	Interconnected	PGE	SANTA CRUZ	SANTA CRUZ	Photovoltaic, External Inverter	0.352440	0.346627	0.0	0.0	...	NaT	No	Enact Systems Inc	No	NaN	No	867193.0000	2.501804	2.0	NEMMT
548964	PGE	Interconnected	PGE	WATSONVILLE	SANTA CRUZ	Photovoltaic, External Inverter	0.046368	0.045468	0.0	0.0	...	NaT	No	BLACK & VEATCH CONSTRUCTION INC	No	NaN	No	15000.0000	0.329902	2.0	EXPNEM
549543	PGE	Interconnected	PGE	SANTA CRUZ	SANTA CRUZ	Photovoltaic, External Inverter	0.016104	0.015943	0.0	0.0	...	NaT	No	JUST LEAKS INCORPORATED	No	NaN	No	57338.0000	3.596437	2.0	SNEM
550281	PGE	Interconnected	PGE	SANTA CRUZ	SANTA CRUZ	Photovoltaic, External Inverter	0.047267	0.046536	0.0	0.0	...	NaT	No	SLINGSHOT POWER INC	No	NaN	NaN	0.0001	0.000000	2.0	EXPNEM
552335	PGE	Interconnected	PGE	SCOTTS VALLEY	SANTA CRUZ	Photovoltaic, External Inverter	0.187880	0.184869	0.0	0.0	...	NaT	No	MYNT SYSTEMS INC	No	NaN	No	440787.0000	2.384320	2.0	EXPNEM
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
2091815	PGE	Interconnected	PGE	WATSONVILLE	SANTA CRUZ	Photovoltaic	0.017520	0.017006	0.0	0.0	...	NaT	No	SOLAR SYMPHONY CONSTRUCTION INC	No	NaN	No	51219.0000	3.011819	2.0	SNEM
2093551	PGE	Interconnected	PGE	SANTA CRUZ	SANTA CRUZ	Photovoltaic	0.020020	0.019438	0.0	0.0	...	NaT	No	ALLTERRA SOLAR	No	NaN	No	86700.0000	4.460335	2.0	SNEM
2094780	PGE	Interconnected	PGE	SCOTTS VALLEY	SANTA CRUZ	Photovoltaic	0.025666	0.025377	0.0	0.0	...	NaT	No	1ST LIGHT ENERGY INC	No	NaN	No	71422.0000	2.814438	2.0	SNEM
2107673	PGE	Interconnected	PGE	SCOTTS VALLEY	SANTA CRUZ	Photovoltaic	0.011328	0.010982	0.0	0.0	...	NaT	No	ALLTERRA SOLAR	No	NaN	No	65000.0000	5.918776	2.0	SNEM
2113657	PGE	Interconnected	PGE	SANTA CRUZ	SANTA CRUZ	Photovoltaic	0.008496	0.008236	0.0	0.0	...	NaT	No	ALLTERRA SOLAR	No	NaN	No	38000.0000	4.613890	2.0	SNEM

	System Size DC	Nbr Applications
2013	1.344600	28
2014	2.927806	17
2015	0.301077	9
2016	2.005947	27
2017	2.316343	23
2018	0.909916	18
2019	1.300814	20
2020	1.213766	23
2021	2.302869	34
2022	2.338809	24
2023	3.310871	57
2024	0.077753	4
2025	0.107215	7

Input	Lower Bound	Baseline	Upper Bound
System Price (\$/kW)	4,000	3,500	3,000
Annual Production (kWh)	43,300	45,000	45,800
Annual System Degradation (%)	0.6	0.5	0.4
Electricity Price (\$/kWh)	0.35	0.39	0.43
Annual Rate Increase (%)	2.75	3.5	6

	Production (kWh)	Cumulative Savings ($)
1	43,300	15,155
2	43,040	30,633
3	42,782	46,442
4	42,525	62,588
5	42,270	79,078
6	42,016	95,920
7	41,764	113,122
8	41,514	130,690
9	41,265	148,633
10	41,017	166,959
11	40,771	185,677
12	40,526	204,793
13	40,283	224,317
14	40,042	244,258
15	39,801	264,624
16	39,562	285,425
17	39,325	306,670
18	39,089	328,367
19	38,855	350,528
20	38,622	373,162
21	38,390	396,278
22	38,159	419,888
23	37,930	444,001
24	37,703	468,629
25	37,477	493,782

Impact Analysis on AB1104 for Santa Cruz County¶

Economic Impact Analysis¶

Environmental Cost Analysis¶

Santa Cruz Commercial & Industrial Projects¶

Commercial and Industrial Projects in Santa Cruz County¶

DGStats Data Gap¶

System Sizes in the years 2021-25¶

Solar Application Processing Times¶

Total Added Capacity in 2021-25¶

Electricity Price¶

Solar Installation Cost Savings¶

Lower Bound¶

Baseline¶

Upper Bound¶

Lost Opportunity Cost:¶

Environmental Impact¶